Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    หาร
    -0.07
     présence
    -0.07
    nivers
    -0.07
    素敵
    -0.07
     Việc
    -0.06
    _factory
    -0.06
    퓭
    -0.06
    Ӏ
    -0.06
     funcionários
    -0.06
     Catholic
    -0.06
    POSITIVE LOGITS
     quil
    0.08
    Weight
    0.08
     Define
    0.07
    	be
    0.07
    passwd
    0.07
    ¸
    0.07
    (dataset
    0.07
     meilleur
    0.07
    \",\
    0.07
    ”,
    0.07
    Act Density 0.543%

    No Known Activations